Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Ad-Superpowers/ad-superpowers-plugin --skill ga4-predictive-audiencesgit clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/ga4-predictive-audiences)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/ga4-predictive-audiences"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/ga4-predictive-audiences/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/ga4-predictive-audiences"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/ga4-predictive-audiences.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.03956 |
| Opus 5.5 | $0.00038 | $0.01582 |
| Sonnet 5.5 | $0.00019 | $0.00791 |
| Haiku 4.5 | $0.00010 | $0.00396 |
Grade A, and why
ga4-predictive-audiences scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GA4 Predictive Audiences Guide
Complete guide for using GA4's machine learning predictive audiences for advanced remarketing and Smart Bidding optimization.
Predictive Metrics Overview
GA4 PREDICTIVE METRICS
======================
┌──────────────────────┬──────────────────────────────────────────────────┐
│ Metric │ Description │
├──────────────────────┼──────────────────────────────────────────────────┤
│ Purchase probability │ Probability that an active user will purchase │
│ │ within the next 7 days │
│ │ Range: 0-100% │
│ │ Updates: daily │
├──────────────────────┼──────────────────────────────────────────────────┤
│ Churn probability │ Probability that an active user will churn │
│ │ (no activity) within the next 7 days │
│ │ Range: 0-100% │
├──────────────────────┼──────────────────────────────────────────────────┤
│ Predicted revenue │ Expected revenue from a user in the next 28 │
│ │ days, based on historical behavior │
│ │ In property currency │
└──────────────────────┴──────────────────────────────────────────────────┘
HOW IT WORKS:
─────────────
├── Google's ML models analyze user behavior
├── Trained on your property data
├── Requires minimum data volume to work
├── Updates daily for all eligible users
└── No extra implementation needed (as long as purchase event is correct)
Eligibility Requirements
REQUIREMENTS FOR PREDICTIVE AUDIENCES
======================================
CRITICAL REQUIREMENTS - All must be met:
1. PURCHASE EVENTS
──────────────────
┌────────────────────────────────────────────────────────────────────────┐
│ Requirement: Minimum 1,000 purchasers AND 1,000 non-purchasers │
│ in 7 days │
│ │
│ This means: │
│ ├── Active e-commerce tracking with purchase event │
│ ├── Sufficient traffic (typically >10,000 users/week) │
│ ├── Purchase event must be correctly configured │
│ └── Consistent data over time (no gaps) │
└────────────────────────────────────────────────────────────────────────┘
2. CHURN PREDICTIONS
────────────────────
┌────────────────────────────────────────────────────────────────────────┐
│ Requirement: Minimum 1,000 churners AND 1,000 active users │
│ in 7 days │
│ │
│ This means: │
│ ├── Sufficient returning users │
│ ├── Clear churn definition (7 days no activity) │
│ └── Consistent engagement tracking │
└────────────────────────────────────────────────────────────────────────┘
3. GENERAL REQUIREMENTS
───────────────────────
┌─────────────────────────┬──────────────────────────────────────────────┐
│ Requirement │ Details │
├─────────────────────────┼──────────────────────────────────────────────┤
│ Model quality │ Sufficient predictive power │
│ │ Google evaluates automatically │
├─────────────────────────┼──────────────────────────────────────────────┤
│ Sustained data │ Consistent volume over 28+ days │
│ │ No large gaps in data │
├─────────────────────────┼──────────────────────────────────────────────┤
│ Purchase event params │ Correct value and currency parameters │
│ │ Transaction ID for deduplication │
├─────────────────────────┼──────────────────────────────────────────────┤
│ User identification │ Consistent user_id or client_id │
│ │ Cross-device tracking helps │
└─────────────────────────┴──────────────────────────────────────────────┘
CHECKING ELIGIBILITY:
────────────────────
Location: Admin → Audiences → New audience → Predictive
├── Green checkmark = Eligible
├── Yellow warning = Almost eligible
└── Grey = Not eligible (hover for reason)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 468 lines · 95 tokens per session scan A 5baf6ea18298
ga4-predictive-audiences is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 95 tokens to every session and 3,956 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.
Other skills, from other repositories
analytics
Growth analytics authority — GA4 event tracking, conversion funnels, attribution models, cohort analysis, A/B testing, Supabase analytics queries, and revenue reporting patterns.
creative-generate
A workflow for creating advertising images and banners from a strategy brief. It separates the main visual artwork from the accurately typeset text and produces variants for display or social formats.
cro-optimizer
CRO specialist that pulls live analytics data via the Humblytics MCP, analyzes conversion funnels, identifies drop-off points, and generates prioritized A/B test hypotheses. Use when analyzing conversion rates, diagnosing funnel leaks, optimizing signup flows, or creating test roadmaps. Triggers: CRO, conversion rate…
learn
Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use…
lead-form-create
Create a Meta Instant Form (Lead Ad form) through a one-question-at-a-time interview. Use when the user asks to create a lead form, Instant Form, CV form, or similar. The agent collects required parameters via a guided dialogue, confirms, then calls metaadsleadformscreate. Also use when the user asks in Japanese…
ai-hive-simulate-dn-samuel
A research and content-planning workflow that studies DN-Samuel's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.